A Metric to Measure Contribution of Nodes in Neural Networks

Jung, Jay Hoon; Shin, Yun‐Jeong; Kwon, Young‐Min

doi:10.1109/ssci44817.2019.9002851

Cited by 3 publications

(2 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final evaluation results, that is, mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) along with the actual versus predicted trend was obtained by averaging the results derived at the end of each iteration (i.e., at the end of stratified 10 cross‐fold validation procedure carried out by Orange data mining tool). Neural networks are sensitive to the number of neurons in the hidden layer, 36 number of hidden layers, number of features in the dataset, as well as the activation function. Determining the number of neurons is critical since selecting too few or too many neurons can lead to under and over‐fitting respectively 37–39 …”

Section: Resultsmentioning

confidence: 99%

Implementation of chemometrics, design of experiments, and neural network analysis for prior process knowledge assessment, failure modes and effect analysis, scale‐down model development, and process characterization for a chromatographic purification of Teriparatide

Pathak

Pokhriyal

Gandhi

et al. 2022

Biotechnology Progress

View full text Add to dashboard Cite

Process understanding and characterization forms the foundation, ensuring consistent and robust biologics manufacturing process. Using appropriate modeling tools and machine learning approaches, the process data can be monitored in real time to avoid manufacturing risks. In this article, we have outlined an approach toward implementation of chemometrics and machine learning tools (neural network analysis) to model and predict the behavior of a mixed-mode chromatography step for a biosimilar (Teriparatide) as a case study. The process development data and process knowledge was assimilated into a prior process knowledge assessment using chemometrics tools to derive important parameters critical to performance indicators (i.e., potential quality and process attributes) and to establish the severity ranking for the FMEA analysis. The characterization data of the chromatographic operation are presented alongwith the determination of the critical, key and non-key process parameters, set points, operating, process acceptance and characterized ranges. The scale-down model establishment was assessed using traditional approaches and novel approaches like batch evolution model and neural network analysis. The batch evolution model was further used to demonstrate batch monitoring through direct chromatographic data, thus demonstrating its application for continuos process verification. Assimilation of process knowledge through a structured data acquisition approach, built-in from process development to continuous process verification was demonstrated to result in a data analytics driven model that can be coupled with machine learning tools for real time process monitoring. We recommend application of these approaches with the FDA guidance on stage wise process development and validation to reduce manufacturing risks.

show abstract

Section: Resultsmentioning

confidence: 99%

Implementation of chemometrics, design of experiments, and neural network analysis for prior process knowledge assessment, failure modes and effect analysis, scale‐down model development, and process characterization for a chromatographic purification of Teriparatide

Pathak

Pokhriyal

Gandhi

et al. 2022

Biotechnology Progress

View full text Add to dashboard Cite

show abstract

“…where α i,j , and c j are constants valid within a polytopeshape linear region defined by the combinations of the ReLU functions of each unit in each layer [4], [19]- [21].…”

Section: B Output Layers With Respect To Input Layermentioning

confidence: 99%

A Metric to Compare Pixel-Wise Interpretation Methods for Neural Networks

Jung

Kwon

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

There are various pixel-based interpretation methods such as saliency map, gradient×input, DeepLIFT, integrated-gradient-n, etc. However, it is difficult to compare their performance as it involves human cognitive processes. We propose a metric that can quantify the distance from the importance scores of the interpretation methods to human intuition. We create a new dataset by adding a simple and small image, named as a stamp, to the original images. The importance scores for the deep neural networks to classify the stamped and regular images are calculated. Ideally, the pixel-based interpretation has to successfully select the stamps. Previous methods to compare different interpretation methods are useful only when the scale of the importance scores is the same. Whereas, we standardize the importance scores and define the measure to ideal scores. Our proposed method can quantitatively measure how the interpretation methods are close to human intuition.

show abstract

Boundaries of Single-Class Regions in the Input Space of Piece-Wise Linear Neural Networks

Jung

Kwon

2021

2020 25th International Conference on Pattern Recognition (ICPR)

View full text Add to dashboard Cite

A Metric to Measure Contribution of Nodes in Neural Networks

Cited by 3 publications

References 6 publications

Implementation of chemometrics, design of experiments, and neural network analysis for prior process knowledge assessment, failure modes and effect analysis, scale‐down model development, and process characterization for a chromatographic purification of Teriparatide

Implementation of chemometrics, design of experiments, and neural network analysis for prior process knowledge assessment, failure modes and effect analysis, scale‐down model development, and process characterization for a chromatographic purification of Teriparatide

A Metric to Compare Pixel-Wise Interpretation Methods for Neural Networks

Boundaries of Single-Class Regions in the Input Space of Piece-Wise Linear Neural Networks

Contact Info

Product

Resources

About